Byakugan: Private, open-source AI-text checker

Name: Byakugan: Private, open-source AI-text checker
Author: JayOfemi

@JayOfemi

Repository

About Byakugan: Private, open-source AI-text checker

A private, open-source AI-text checker, as a browser app and an MCP server, all on your own machine.

#checker #aichecker #aitextchecker #ai-detector #ai-text-detection #chatgpt-detector #ai-content-detector #grammar-checker #plagiarism-checker #on-device #privacy #open-source #oss

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "ai-checker": {
      "command": "npx",
      "args": [
        "-y",
        "@jayofemi/ai-checker"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Byakugan: Private, open-source AI-text checker?

Byakugan: Private, open-source AI-text checker is an MCP server that gives AI assistants local detection, phrase-level tell identification, reuse checking against provided references, and grammar analysis. It runs entirely on the user’s machine and ships as both an MCP server and a TypeScript library.

How to use Byakugan: Private, open-source AI-text checker?

Add the server to your MCP client’s config with the command npx -y @jayofemi/ai-checker. For Claude Desktop, open Settings → Developer → Edit Config and insert the JSON block. After restarting, ask the assistant in plain language, for example: “use ai-checker to check whether this reads as AI” and paste your text. The server returns analysis; the assistant rewrites from it.

Key features of Byakugan: Private, open-source AI-text checker

detect_ai_text returns a 0–100 likelihood with per-signal breakdown and confidence band.
find_ai_tells identifies exact character spans that read as AI.
check_reuse performs shingle‑overlap against reference documents you provide.
check_grammar uses a rule‑based grammar and style checker (Harper) with suggested fixes.
All tools are deterministic; the server does not rewrite text itself.
Available as a TypeScript library via npm install @jayofemi/ai-checker.

Use cases of Byakugan: Private, open-source AI-text checker

Checking whether a piece of text reads as AI-generated, with a likelihood score rather than a binary verdict.
Finding and rewriting only the specific phrases that sound formulaic or AI-like.
Comparing a draft against your own reference documents for text reuse (no web search).
Running a local, deterministic grammar and style check on any writing.

FAQ from Byakugan: Private, open-source AI-text checker

What makes Byakugan different from online AI detectors?

It runs completely on your machine, so your text never leaves it. The detection is a directional signal with a confidence band, not a yes/no verdict. The server returns precise analysis for the assistant to act on, rather than rewriting text itself.

What are the runtime requirements?

You need Node.js installed so that npx can run the package. No external API keys or accounts are required.

Where does my data go?

All detection, tell‑finding, reuse checking, and grammar analysis happen locally on your machine. No data is sent to any external website or service.

Are there known limitations?

Detection is biased against non‑native English writers – even, formulaic, stock‑phrase‑heavy writing reads as more AI‑like. The results are a directional signal, not proof, and should be treated as a second opinion.